SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task

By Tao Yu, Michihiro Yasunaga, Kai-Chou Yang, Rui Zhang, Dongxu Wang, Zifan Li, Dragomir R. Radev. 2018

229 citations recorded by the source corpus.

Most existing studies in text-to-SQL tasks do not require generating complex SQL queries with multiple clauses or sub-queries, and generalizing to new, unseen databases. In this paper we propose SyntaxSQLNet, a syntax tree network to address the complex and cross-domain text-to-SQL generation task. SyntaxSQLNet employs a SQL specific syntax tree-based decoder with SQL generation path history and table-aware column attention encoders. We evaluate SyntaxSQLNet on a new large-scale text-to-SQL corpus containing databases with multiple tables and complex SQL queries containing multiple SQL clauses and nested queries. We use a database split setting where databases in the test set are unseen during training. Experimental results show that SyntaxSQLNet can handle a significantly greater number of complex SQL examples than prior work, outperforming the previous state-of-the-art model by 9.5% in exact matching accuracy. To our knowledge, we are the first to study this complex text-to-SQL task. Our task and models with the latest updates are available at https://yale-lily.github.io/seq2sql/spider.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, methodology): “Such domain shifts typically occur across related but different datasets (Torralba & Efros, 2011; Fang et al., 2013; Venkateswara et al., 2017; Yu et al., 2018b; 2019; Peng et al., 2019; Kamath et al., 2020), as well as from synthetic data to real data (including sim2real) (Wang et al., 2015; Ganin…”
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers (2019, methodology): “sults using the same metrics as Yu et al. (2018a): exact match accuracy on all examples, as well as divided by difficulty levels.”
Global Reasoning over Database Structures for Text-to-SQL Parsing (2019, methodology): “We use the ofﬁcial S PIDER script for evaluation, which tests for loose exact match of queries.”
Model-based Interactive Semantic Parsing: A Unified Framework and A Text-to-SQL Case Study (2019, methodology): “3 In our experiments, we follow the same database split as in (Yu et al., 2018c) and report the Exact Matching accuracy (“ Acc em ”) on Dev set.”
SParC: Cross-Domain Semantic Parsing in Context (2019, methodology): “…community by virtue of a continuous effort of dataset creation (Zelle and Mooney, 1996; Iyyer et al., 2017; Zhong et al., 2017; Finegan-Dollak et al., 2018; Yu et al., 2018a) and the modeling innovation that follows it (Xu et al., 2017; Wang et al., 2018; Yu et al., 2018b; Shi et al., 2018).”
Grammar-based Neural Text-to-SQL Generation (2019, methodology): “…98% of instances with minimal over-generation in two popular datasets: ATIS (Hemphill et al., 1990), a dataset of contextual interactions with a ﬂight database, and S PIDER (Yu et al., 2018c), a dataset focused on complex SQL queries over a variety of schemas, many of which are unseen at test time.”
LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs (2021, background): “…work on semantic parsing requires the ground truth programs for training (Zelle & Mooney, 1996; Zettle-moyer & Collins, 2012; Jia & Liang, 2016; Yu et al., 2018b;a; Keysers et al., 2020), some recent approaches have been proposed to improve the model performance with weak supervision, i.e.,…”
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation (2019, methodology): “The large number of OOD words poses another steep challenge in predicting columns in SQL queries (Yu et al., 2018b), because the OOD words usually lack of accurate representations in neural models.”
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL (2023, methodology): “Because there is a huge gap between natural language questions and their corresponding SQL queries, some works have focused on how to design an efﬁcient intermediate representation (IR) to bridge the aforementioned gap (Yu et al. 2018b; Guo et al. 2019; Gan et al. 2021b).”
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (2019, methodology): “(2) SyntaxSQL-con: This is adapted from the original context-agnostic SyntaxSQLNet (Yu et al., 2018b) by using bi-LSTMs to encode the interaction history including the utterance and the associated SQL query response.”
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction (2021, methodology): “…recent text-to-SQL models have been introduced (Yu et al., 2018a; Zhang et al., 2019; Guo et al., 2019; Wang et al., 2020, inter alia) as a result of the availability of SPIDER (Yu et al., 2018b), a large dataset of schema, questions and gold parses spanning several databases in different domains.”
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (2019, methodology): “SyntaxSQL-con SyntaxSQLNet is a SQLspecific syntax-tree based model introduced for Spider (Yu et al., 2018b).”
Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing (2021, methodology): “On Spider, most of work focuses on establishing schema linking, which dynamically obtains the relationships between natural language sentences and database schemas through attention mechanism.”
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing (2020, methodology): “Recent pre-trained language models (LMs) such as BERT (Devlin et al., 2019) and RoBERTa (Liu et al., 2019) achieve tremendous success on a spectrum of natural language processing tasks, including semantic parsing (Zettlemoyer & Collins, 2005; Zhong et al., 2017; Yu et al., 2018b).”